compare-race is agent-read markdown (skill) from ellmos-ai/skills: Use when the user wants to send the same prompt to several LLMs and compare the answers - sequentially (stopwatch, clean per-lane timing) or in parallel (true race), with optional repetitions per model, judged by the starting model across quality, correctness, completeness, instruction fidelity and latency (time is only one dimension). Triggers on /compare-race, 'model race', 'vergleiche modelle', 'gleicher prompt an mehrere modelle'..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
mdr add ellmos-ai/skills/compare-race@v1.0.0mdr add ellmos-ai/skills/compare-race@sha256:eef2d1e681ca3ed6Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_xpemyfgrxbjg3a5n)
0 badge views in 30 days
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-08-23 | f025c2c | 3,232 B | A | view · diff |
| v1.0.0 | 2026-08-17 | f96c5bc | 3,213 B | A | view · diff |
| v1.0.0 | 2026-08-16 | a4beae8 | 3,150 B | A | view |
ellmos-ai/skills · 4 stars · license MIT · pushed 2026-09-06 · branch master
GET https://markdownregistry.com/api/v1/artifacts/art_xpemyfgrxbjg3a5n GET https://markdownregistry.com/api/v1/resolve?ref=ellmos-ai/skills/compare-race GET https://markdownregistry.com/api/v1/blob/eef2d1e681ca3ed6c7fe63a8a36535632cf48a7b990fd8d944c8ef42ea046750